End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the recipe_nlg dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0517
+- Loss: 2.3036
 
 ## Model description
 
@@ -38,8 +38,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 56   | 0.1018          |
-| No log        | 2.0   | 112  | 0.0517          |
+| 2.5638        | 1.0   | 112  | 2.3422          |
+| 2.3798        | 2.0   | 224  | 2.3036          |
 
 
 ### Framework versions

runs/Dec25_10-07-35_5d2b802b7e2b/events.out.tfevents.1735121257.5d2b802b7e2b.20350.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e863c58671b82f9a276b725fe248aa05299b67a28c18e9da82828cad4e8869
-size 6020
+oid sha256:1f646b575be4d21fbe949785f38f3ff7ad7624dc81d97fea5ed54cb6cb8ab131
+size 6645

runs/Dec25_10-07-35_5d2b802b7e2b/events.out.tfevents.1735121754.5d2b802b7e2b.20350.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445278599d19325e24137fd2aebc45aaea6df9b3a8be9f5ed05b922f7bf58b29
+size 359